Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4711 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.1535. Min Act: -0.0000

Data Index: 143300 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.1535. Min Range: -1.1535

Max Act: 1.0738. Min Act: -0.0000

Data Index: 505378 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9263. Min Act: -0.0000

Data Index: 746738 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8473. Min Act: -0.0000

Data Index: 752948 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.9216. Min Act: -0.0000

Data Index: 122540 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1060428 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7945. Min Act: -0.0000

Data Index: 541125 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1280692 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.8380. Min Act: -0.0000

Data Index: 202346 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7426. Min Act: -0.0000

Data Index: 807491 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1008560 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6954. Min Act: -0.0000

Data Index: 465500 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.7181. Min Act: -0.0000

Data Index: 703040 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1238845 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6218. Min Act: -0.0000

Data Index: 584074 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1094115 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6883. Min Act: -0.0000

Data Index: 160450 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6492. Min Act: -0.0000

Data Index: 879009 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1220699 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.1535. Min Range: -1.1535

Max Act: 0.6260. Min Act: -0.0000

Data Index: 54888 (C4 (Web Text))

Max Activating Token Index: 562